Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0356. Min Range: -6.0356
Max Act: 6.0356. Min Act: -0.1700
Data Index: 3163223 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0356. Min Range: -6.0356
Max Act: 6.0356. Min Act: -0.1700
Data Index: 6204307 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0356. Min Range: -6.0356
Max Act: 6.0043. Min Act: -0.1700
Data Index: 5802204 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 3356259 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 816883 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8793. Min Act: -0.1700
Data Index: 6529823 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8793. Min Act: -0.1700
Data Index: 8483690 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8481. Min Act: -0.1700
Data Index: 4848627 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8793. Min Act: -0.1700
Data Index: 5566472 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 8483698 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8168. Min Act: -0.1700
Data Index: 99071 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8481. Min Act: -0.1700
Data Index: 7698578 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8481. Min Act: -0.1700
Data Index: 1358993 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8168. Min Act: -0.1700
Data Index: 7160628 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8168. Min Act: -0.1700
Data Index: 3356264 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8168. Min Act: -0.1700
Data Index: 7824649 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3356263 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3482408 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7543. Min Act: -0.1700
Data Index: 99061 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7543. Min Act: -0.1700
Data Index: 99063 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19